比较 LSTM 结构

Question

我正在尝试根据该图片构建 LSTM 模型。 我是深度学习的初学者，特别是 RNN 结构，所以我需要你的建议来指导我

所以，我正在处理一个包含 70k 用户和 12k 动画的数据框，我的数据框包含：

• 用户标识

• 用户评分

• 动漫ID

• 流派：与动漫相关的标签列表，例如：动作、喜剧、学校...等。

• users_tags：我通过 tfifd 方法和一些与用户相关的文本数据为唯一用户构建的 15 个唯一标签的列表

我的数据框看起来像：

    anime_id    user_id user_rating name    tags    genre
0   1   234 9.0 Cowboy Bebop    drama , fi , mal action , military , sci fi , ...   Action, Adventure, Comedy, Drama, Sci-Fi, Space
1   1   382 10.0    Cowboy Bebop    life , shiki , tv , thriller , movie short , c...   Action, Adventure, Comedy, Drama, Sci-Fi, Space
2   1   160 9.0 Cowboy Bebop    fantasy , action , supernatural , tv , mystery...   Action, Adventure, Comedy, Drama, Sci-Fi, Space
3   1   341 8.0 Cowboy Bebop    action , school , romance , new , short , mal ...   Action, Adventure, Comedy, Drama, Sci-Fi, Space
4   1   490 9.0 Cowboy Bebop    mal adventure , movie short , school , strange...   Action, Adventure, Comedy, Drama, Sci-Fi, 

这里的参数我用于我的模型：

#parameters
users = interactions_full_df.user_id.unique()
animes = interactions_full_df.anime_id.unique()
animes_tags = " ".join(interactions_full_df["genre"].unique()).split(",")
n_animes_tags = len(animes_tags)
n_users = len(users)
n_animes =  len(animes)
n_users_tags = 15

我将 100 用于嵌入层的“潜在暗淡”。

在这里，我尝试构建这个模型。你能说我的方法是否正确吗？

    """ The lstm cell is the concatenation of 3 things : 
--> 1.0  Anime Embedding Vector
--> 2.0 Average of : 
        --> 2.1 Tags embedding vectors associated with the current anime
        --> 2.2 Tags embedding vectors associated with the next anime in a sequence
"""
# 1.0
animes_input = Input(shape=[1],name='Anime')
animes_embedding = Embedding(n_animes + 1, 
                                 latent_dim, 
                                 name='Animes-Embedding')(animes_input)

""" I suppose we need Users embedding to find what's anime chosen by users ??"""
Users_input = Input(shape=[1],name='Users')
Users_embedding = Embedding(n_users + 1, 
                                 latent_dim, 
                                 name='Users-Embeddings')(Users_input)
#2.0
    # 2.1
""" Anime Tags """
animes_tags_input = Input(shape=[1],name='anime_tags')
tags_embedding = Embedding(n_animes_tags + 1, 
                                 latent_dim, 
                                 name='Animes-Tags-embedding')(animes_tags_input)

#2.2 : tags of future anime in a sequence ???
#my input will be a padded sequence of tags used as a string object <<<<<---- 
inp_shape = max_sequence_len - 1
input_len = Input(shape=[inp_shape], name = "future_tags")
sequence_tags_embeddings = Embedding(tags_total_words, latent_dim)(input_len)
sequence_lstm_cells = LSTM(30)(sequence_tags_embeddings)
future_tags_embedding = Dense(latent_dim, activation='softmax')(sequence_lstm_cells) #???????????? i'm not sure at all 
# then average them
averaged_tags = average([tags_embedding, future_tags_embedding])
#then we need to concatenate all of them
merged_cell =  merge([averaged_tags, animes_embedding, Users_embedding])
# My lstm cells is ready : the structure seems to be an Many to One (may be i'm wrong ?)
n_neurons = 100
lstm_cell = LSTM(30, input_shape=(10, 1))(merged_cell)
result = Dense(1, activation='softmax', name = "Recommendation")(lstm_cell)

LSTM_MODEL = Model([animes_input, animes_tags_input, Users_input, input_len], result)
LSTM_MODEL.compile(loss='categorical_crossentropy',
              optimizer='rmsprop')
LSTM_MODEL.summary()

对于“未来标签”的部分，我使用了类似这样的填充标签序列：

def get_sequence_of_tokens(corpus):
    ## tokenization
    tokenizer.fit_on_texts(corpus)
    total_words = len(tokenizer.word_index) + 1

    ## convert data to sequence of tokens 
    input_sequences = []
    for line in corpus:
        token_list = tokenizer.texts_to_sequences([line])[0]
        for i in range(1, len(token_list)):
            n_gram_sequence = token_list[:i+1]
            input_sequences.append(n_gram_sequence)
    return input_sequences, total_words

def generate_padded_sequences(input_sequences, input_total_words):
    max_sequence_len = max([len(x) for x in tqdm(input_sequences)])
    input_sequences = np.array(pad_sequences(input_sequences, maxlen=max_sequence_len, padding='pre'))
    predictors, label = input_sequences[:,:-1],input_sequences[:,-1]
    label = ku.to_categorical(label, num_classes=input_total_words)
    return predictors, label, max_sequence_len

print("create list ..")
train_tags_anime_list = [get_tags_anime(anime_id) for anime_id in tqdm(train["anime_id"])]
test_tags_anime_list = [get_tags_anime(anime_id) for anime_id in tqdm(valid["anime_id"])]
print("cleaning ...")
train_tags_corpus = [clean_text(x) for x in tqdm(train_tags_anime_list)]
valid_tags_corpus = [clean_text(x) for x in tqdm(test_tags_anime_list)]
print("tokenization ..")
train_tags_inp_sequences, train_tags_total_words = get_sequence_of_tokens(train_tags_corpus)
valid_tags_inp_sequences, valid_tags_total_words = get_sequence_of_tokens(valid_tags_corpus)
print("padd sequence")
train_tags_predictors, train_tags_label, train_max_sequence_len = generate_padded_sequences(train_tags_inp_sequences, train_tags_total_words)
valid_tags_predictors, valid_tags_label, valid_max_sequence_len = generate_padded_sequences(valid_tags_inp_sequences, valid_tags_total_words)

Answer 1

你想构建一个Stacked LSTM网络，具有多个特征（你命名的参数通常称为特征），这在https://machinelearningmastery.com/stacked-long-short-term-memory-networks/和https://machinelearningmastery.com/use-features-lstm-networks-time-series-forecasting/和https://datascience.stackexchange.com/questions/17024/rnns-with-multiple-features中有描述

RNN 和 LSTM 只能处理顺序数据，但是这可以通过具有多个维度的特征向量进行扩展（您的参数集合如https://datascience.stackexchange.com/questions/17024/rnns-with-multiple-features 中的答案所述)

2 层中 6 个 LSTM 单元的显示结构是具有 2 层 feature_dim = data_dim=6 (or 7)（参数/特征的数量）和 timesteps=3（2 层，每层 3 个单元）的 Stacked LSTM 网络 cf section 用于序列分类的堆叠 LSTM 在 https://keras.io/getting-started/sequential-model-guide/ 和 How to stack multiple lstm in keras? 中用于 keras 代码。

设置准确的输入形状至关重要，参见 Understanding Keras LSTMs，您的网络是多对多的情况。 传递给 LSTM 的输入形状应为 (num_samples,timesteps,data_dim) 形式，其中 data_dim 是特征向量或参数向量

嵌入层用于 One-Hot 编码 cf https://towardsdatascience.com/deep-learning-4-embedding-layers-f9a02d55ac12 对于 keras 代码请参阅 https://towardsdatascience.com/deep-learning-4-embedding-layers-f9a02d55ac12 和 https://keras.io/layers/embeddings/ ，也许您也可以使用简单的 标签编码 ( http://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.LabelEncoder.html , http://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.OneHotEncoder.html#sklearn.preprocessing.OneHotEncoder )